Virtual Space Topic Identification with Machine Learning Workflow Triggers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing communication platforms face inefficiencies in responding to user inquiries within virtual spaces due to the manual and time-consuming process of administrative users reading, drafting, and answering numerous questions, especially in channels with voluminous posts, making it difficult to find relevant information quickly.
Innovation Solution
Utilizing machine learning models trained on interaction data to determine topics associated with user requests, assigning confidence levels, and displaying graphical identifiers to trigger workflow responses, thereby reducing the need for manual administrative intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If administrative users manually read, draft, and answer user questions in communication channels, then personalized and context-aware responses can be provided, but the process becomes time-consuming and inefficient especially in channels with voluminous posts
Solution Approach 1:
The patent introduces machine learning models as intermediaries between user questions and administrative users. The ML models automatically analyze channel history and user inquiries to generate draft responses, which administrative users then review and refine. This intermediary system handles the time-consuming aspects of information retrieval and initial response formulation, allowing administrative users to focus on ensuring accuracy and appropriateness of responses.
Solution Approach 2:
The system performs preliminary actions by automatically analyzing channel history, identifying relevant information, and generating draft responses before administrative users need to intervene. The ML models pre-process incoming questions by searching channel archives, extracting key context, and formulating initial response drafts, thereby reducing the time administrative users spend on each inquiry while maintaining response quality.
2Loss of information
If users search through voluminous channel history to find relevant information, then they can access past discussions and answers, but the process becomes difficult and nearly impossible to find relevant information quickly
Solution Approach 1:
The patent replaces the mechanical manual search process with an automated machine learning-based information retrieval system. Instead of users manually scrolling and searching through channel history, the ML models automatically analyze the incoming question, search relevant channel archives, identify pertinent past discussions and answers, and present synthesized results to users. This substitution transforms an inefficient manual process into an automated intelligent system that quickly retrieves relevant information.
Solution Approach 2:
The system enables self-service by allowing the ML models to autonomously perform information retrieval and analysis without requiring user intervention in the search process. When users post questions, the system automatically searches channel history, identifies relevant past discussions, and presents findings to users, eliminating the need for users to manually navigate through voluminous channel data.
3Adaptability or versatility
If manual administrative intervention is used to respond to user inquiries, then responses can be customized and context-aware, but the process requires significant time and effort from administrative users
Solution Approach 1:
The patent introduces machine learning models as intermediaries that handle the initial analysis and draft generation, while administrative users provide final oversight and customization. The ML models analyze user inquiries, search channel history, and generate context-aware draft responses, which administrative users then review and refine as needed. This intermediary approach maintains response quality and adaptability while significantly increasing the number of responses that can be handled per unit time.
Solution Approach 2:
The system changes the operational parameters by shifting from purely manual response generation to an automated-assisted model. The ML models handle routine analysis and draft creation, freeing administrative users to focus on complex cases requiring high customization. This parameter change in the workflow enables the system to handle a higher volume of inquiries while maintaining the ability to customize responses when necessary.
Data Source
AI summary
Techniques for displaying workflow responses based on determining topics associated with user requests are discussed herein. In some examples, a user may post a request (e.g., question) to a virtual space (e.g., a channel, thread, board, etc.) of a communication platform. The communication platform may input the request into a machine learning model trained to identify topics associated with the request and confidence levels associated with topics. In such examples, the communication platform may associate a topic with the user request based on the confidence level of the topic. In some examples, the communication platform may determine that the topic is associated with a graphical identifier (e.g., emoji). The communication platform may cause the graphical identifier to be displayed to the virtual space within which the user request was posted. In response to displaying the graphical identifier, the communication platform may display a workflow response to the virtual space.